文献速递儿童口腔

基于深度学习的儿童龋齿检测原型人工智能系统的开发

[Development of a deep learning based prototype artificial intelligence system for the detection of dental caries in children].
PubMed 文献 · Zhonghua Kou Qiang Yi Xue Za Zhi · 2021-01-01

研究收集北京大学口腔医学院儿童口腔科2013年10月至2020年6月全身麻醉治疗前患儿单颌口内照片712张,经标注后建立深度学习人工智能系统,以龋坏概率大于50.0%为判断标准。测试集对成洞龋、未成洞窝沟龋、未成洞邻面龋的灵敏度分别为96.0%、95.8%、88.1%,特异度分别为97.0%、99.0%、97.1%。结论认为该系统具备判断龋坏及不同龋类型的能力。

要点

  • 基于712张单颌口内照片建立深度学习儿童龋齿识别系统雏形。
  • 测试集对成洞龋灵敏度96.0%、特异度97.0%。
  • 测试集对未成洞窝沟龋灵敏度95.8%、特异度99.0%;对未成洞邻面龋灵敏度88.1%、特异度97.1%。

核心结论

  • 本研究构建的儿童龋人工智能识别系统雏形具备判断龋坏的能力,对同组样本不仅能准确判断成洞龋,对未成洞的窝沟龋、边缘嵴釉质未破坏的邻面龋也能准确判断。

研究设计与样本

  • 收集北京大学口腔医学院·口腔医院儿童口腔科2013年10月至2020年6月拍摄的符合纳入标准的全身麻醉治疗前患儿单颌口内数码照片712张。
  • 以记录完备的治疗后病历诊断结合口内像确定牙齿是否龋坏及龋类型,由儿童口腔科医师使用VoTT软件(Windows 2.1.0,Microsoft,美国)标注。
  • 分5个标签组:未成洞窝沟龋、未成洞邻面龋、完好无龋坏的牙齿邻面、成洞龋及无龋牙(含已完好充填的牙齿)。
  • 每个标签组数据按6.4∶1.6∶2.0的比例采用随机数表方法随机分为训练集、验证集和测试集。
  • 采用标注后的训练数据集进行深度学习训练,建立龋齿人工智能识别系统,以龋坏概率大于50.0%作为患龋的判断标准。

主要发现

  • 712张单颌口内照片经分割标注得到未成洞窝沟龋953张、未成洞邻面龋1002张、成洞龋3008张、无龋牙3189张、无龋邻面862张,共计9014张图像数据。
  • 测试集对成洞龋识别灵敏度和特异度分别为96.0%和97.0%。
  • 测试集对未成洞窝沟龋灵敏度为95.8%,特异度99.0%。
  • 测试集对未成洞邻面龋灵敏度为88.1%,特异度97.1%。

关键数值与推荐

  • 以龋坏概率大于50.0%作为患龋的判断标准输出判断结果。
  • 应用灵敏度、特异度等作为识别各类龋坏准确性的指标评价人工智能系统的判断能力。

临床怎么用

  • 原文未据此给出临床推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Objective: To develop a prototype artificial intelligence image recognition system for detecting dental caries, especially those without cavities, in children. Methods: Seven hundred and twelve intraoral photos, which were taken by dental professionals using a digital camera from October 2013 to June 2020 in the Department of Pediatric Dentistry, Peking University School and Hospital of Stomatology, were collected from the children who received dental treatment under general anesthesia. The well-documented post-treatment electronic dental record of each child was identified as label standard to determine whether the teeth were carious and the type of caries types such as caries that had become cavities (caries with cavities), pit and fissure caries that had not become cavities (pit and fissure caries) and proximal caries which the marginal ridge enamel had not been destroyed (proximal caries). The various teeth and caries types were labeled by pediatric dentists using VoTT software (Windows 2.1.0, Microsoft, U S A). There were five labeled groups: pit and fissure caries, approximal caries, non-carious approximal surfaces, caries with cavities and teeth without caries (including intact fillings). Each group was randomly divided into training dataset, validation dataset and test dataset at a ratio of 6.4∶1.6∶2.0 by using random number table. After using the labeled training dataset for deep learning training, a deep learning-based artificial intelligence (AI) image recognition system for detecting dental caries was established, with the caries probability greater than 50.0% as the criterion for determining caries. Sensitivity and accuracy were used as indicators of recognition specificity. Results: Seven hundred and twelve single-jaw intraoral photographs were segmented and annotated into 953 pit and fissure caries, 1 002 approximal caries, 3 008 caries with cavities, 3 189 teeth without caries and 862 non-carious approximal surfaces, totaly 9 014 labels. The sensitivities and specificities of the test set were 96.0% and 97.0% for caries with cavities, 95.8% and 99.0% for pit and fissure caries and 88.1% and 97.1% for approximal caries. Conclusions: The current AI system developed based on deep learning of the intra-oral photos in the present study showed the ability to detect dental caries. Furthermore, the AI system could accurately verify different types of dental caries such as caries with cavities, pit and fissure caries and proximal caries. 目的: 通过深度学习的方法,开发具备判断儿童牙齿是否龋坏尤其是判断未成洞龋能力的人工智能识别系统雏形。 方法: 收集北京大学口腔医学院·口腔医院儿童口腔科2013年10月至2020年6月拍摄的符合纳入标准的全身麻醉治疗前患儿单颌口内数码照片712张,以记录完备的治疗后病历诊断结合口内像确定牙齿是否龋坏以及龋的类型,具体包括:已成洞的龋(成洞龋)、未成洞的窝沟龋、边缘嵴釉质未破坏的邻面龋(未成洞邻面龋)。由儿童口腔科医师使用VoTT软件(Windows 2.1.0,Microsoft,美国)对不同牙齿及龋坏类型进行标注。分5个标签组:未成洞窝沟龋、未成洞邻面龋、完好无龋坏的牙齿邻面、成洞龋及无龋牙(含已完好充填的牙齿);每个标签组数据按6.4∶ 1.6∶ 2.0的比例采用随机数表的方法随机分为训练集、验证集和测试集数据。采用标注后的训练数据集进行深度学习训练,并建立龋齿人工智能识别系统,以龋坏概率大于50.0%作为患龋的判断标准输出判断结果,并对测试集数据进行识别。应用灵敏度、特异度等作为识别各类龋坏准确性的指标评价人工智能系统的判断能力。 结果: 712张单颌口内照片经分割标注得到未成洞窝沟龋953张,未成洞邻面龋1 002张,成洞龋3 008张,无龋牙3 189张,无龋邻面862张,共计9 014张图像数据。测试集的识别结果:对成洞龋识别灵敏度和特异度分别为96.0%和97.0%;对未成洞窝沟龋灵敏度为95.8%,特异度99.0%;对未成洞邻面龋灵敏度为88.1%,特异度97.1%。 结论: 本研究构建的儿童龋人工智能识别系统雏形,具备判断龋坏的能力,对同组样本该系统不仅能准确判断成洞龋,对未成洞的窝沟龋、边缘嵴釉质未破坏的邻面龋也能准确判断。.

来源:Zhonghua Kou Qiang Yi Xue Za Zhi,查看原文。版权归原作者所有。

引用

  1. Li RZ, Zhu JX, Wang YY, et al. [Development of a deep learning based prototype artificial intelligence system for the detection of dental caries in children]. Zhonghua Kou Qiang Yi Xue Za Zhi. 2021. PMID: 34915661. doi:10.3760/cma.j.cn112144-20210712-00323

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。